cs.CVNov 13, 2026

DySENSE: Dynamic Spatiotemporal ENergy Synthesis and Emulation with Satellite Imagery

Authors: Kailai Sun, Zijie Gao, Mingyi He, Can Rong, Alok Prakash, Baoshen Guo, Shenhao Wang, Jinhua Zhao

Organizations: SMART, Singapore · Massachusetts Institute of Technology, Cambridge, MA, USA · National University of Singapore, Singapore · University of Florida, Gainesville, FL, USA

Abstract

Cities account for over two-thirds of the world's energy and more than 70% of global carbon dioxide emissions. City energy is essential for achieving the 2050 net-zero target and the UN's Sustainable Development Goals 7 and 11. Although existing studies have made progress, they are limited by data and methodological gaps. Existing studies are largely predictive for existing cities rather than generative for future cities; fine-grained, aligned monthly dynamic energy data are scarce; and existing GenAI models struggle to generate dynamic urban functional monthly energy. We present DySENSE, a joint multimodal GenAI framework that synthesizes static urban satellite imagery together with spatially aligned, dynamic monthly building energy consumption maps. We decouple long-term static urban morphology from short-term dynamic energy consumption. By conditioning on static urban land use, DySENSE can generate realistic, diverse and new static urban imagery with aligned energy maps. By conditioning on dynamic monthly and climate prompts, DySENSE can jointly generate dynamic, monthly energy consumption maps while keeping the urban morphology static. Experiments across four cities (New York, Washington, Norfolk, Busan) demonstrated that DySENSE can generate annotated high-fidelity synthetic energy data using less than 25% labelled data, boosting downstream prediction performance by 8% mIoU, and achieving strong energy dynamic consistency. Compared to existing methods, DySENSE significantly improved prediction performance (8.7% accuracy) and reduced prediction error (9%-18% CVRMSE, ASHRAE). DySENSE offers an effective foundation for energy-efficient cities, peak-load analysis, building performance simulation and dynamic demand response for city, energy, and building science. The data and code: https://huggingface.co/datasets/skl24/MUSE2 and https://github.com/kailaisun/DySENSE

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. SENSE: Satellite-based ENergy Synthesis for Sustainable Environment

    May 18, 2026Kailai Sun, Mingyi He, Heye Huang +5Conditional Image GenerationSynthetic Data Generation

  2. SynEnergy: Anomaly Semantic-Guided Diffusion for Synthetic Energy Data Generation

    Aug 4, 2026Lin Jiang, Dahai Yu, Ravikumar Gelli +1Synthetic Data GenerationTime Series Generation

  3. HeatPrompt: Zero-Shot Vision-Language Modeling of Urban Heat Demand from Satellite Images

    Feb 23, 2026Kundan Thota, Xuanhao Mu, Thorsten Schlachter +1Building Energy ModelingBuilding Energy Management